Unlock instant, AI-driven research and patent intelligence for your innovation.

A uniform GMM image matching method based on fusion space and feature information

A matching method and feature information technology, applied in the field of computer vision, can solve the problem of low image matching accuracy and achieve the effect of improving accuracy

Active Publication Date: 2019-06-14
HUAZHONG UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to solve the technical problem of the prior art that the Gaussian component only contains spatial information and the image matching accuracy is low

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A uniform GMM image matching method based on fusion space and feature information
  • A uniform GMM image matching method based on fusion space and feature information
  • A uniform GMM image matching method based on fusion space and feature information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0043] Such as figure 1 As shown, an image matching method based on a uniform GMM that fuses spatial and feature information, the image to be matched is image I 1 and I 2 , the method includes the following steps:

[0044] Step S1. Extract image I 1 The feature points get the data point set X={x i , g i |x i ∈ R 2 , g i ∈ R 128 ,i=1,...,n}, extract image I 2 The feature points of the model point set Y={y j , h j |y j ∈ R 2 , h j ∈ R 128 ,j=1,...,m}, n represents the image I 1 The number of feature points extracted in , m represents the image I 2 The number of feature points extracte...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a uniform GMM image matching method based on fusion space and feature information. A Gaussian mixture model which effectively fuses spatial information and feature informationis adopted. The Gaussian component weight coefficient is not added with the priori information, the Gaussian component contains the spatial information and the feature information at the same time, and the solution of the matching relation is determined by the spatial information and the feature information at the same time. When the model points in the model point set and a certain data point inthe data set meet the condition that the feature descriptors are similar or the spatial positions are aligned, the two points are likely to form a pair of matching, so that the image matching accuracyis improved.

Description

technical field [0001] The invention belongs to the field of computer vision, and more specifically relates to an image matching method based on a uniform GMM that fuses space and feature information. Background technique [0002] Image feature point matching is the process of finding the corresponding relationship of feature points between two images. Among many methods for finding correspondence between point sets, a method based on Gaussian Mixture Model (GMM) has been widely used in point set registration in recent years. Their core idea is to regard one of the point sets as the center of the GMM, called the model point set; regard the other point set as a sample conforming to the GMM, called the data point set. Then, by learning a spatial transformation function, the model point set is gradually moved towards the data point set until the two point sets are aligned. In the uniform Gaussian mixture model (Uniform Gaussian Mixture Model, UGMM) framework, all GMM componen...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62
Inventor 陶文兵刘银凤
Owner HUAZHONG UNIV OF SCI & TECH